Web JARVIS

logo
main page with speech recognition
html toggle
defang monitoring

Inspiration

Our inspiration stemmed from the desire to create a more intuitive and engaging way for users to interact with technology. By leveraging speech recognition similar to ChatGPT, we aimed to develop an interactive chat interface that allows users to build websites using voice commands. This approach enhances user engagement and simplifies the web development process for non-technical users.

What it does

The application enables users to communicate with a chatbot through voice input, creating a seamless and interactive chat experience. It captures spoken words, processes them, and generates a web page based on the user's input. This functionality transforms the traditional web development process into an accessible and user-friendly experience.

How we built it

We utilized Flask for the backend, HTML for the web structure, and JavaScript for interactivity. The Web Speech API was integrated to facilitate voice input, allowing users to interact with the application naturally. The chat interface dynamically updates with responses using HTML and JavaScript. We deployed the project using Defang CLI, which employs ECS with Docker and Docker Compose for streamlined deployment.

Challenges we ran into

One significant challenge was managing discrepancies between local and production environments. While manipulating static files locally was straightforward, deploying them in a Dockerized environment on ECS proved complex. We had to adjust Docker configurations to ensure seamless functionality across different environments.

Accomplishments that we're proud of

We are proud of developing a functional prototype that captures voice input and generates an instant web page based on user commands. This achievement highlights the potential for creating intuitive user interfaces and represents a step forward in making coding accessible to everyone.

What we learned

This project deepened our understanding of client-server interactions and real-time audio processing. We also gained valuable insights into integrating diverse web technologies to create a cohesive user experience. Additionally, we learned how to navigate discrepancies between local and production environments in ECS by effectively modifying Docker and Docker Compose configurations.

What's next for Web JARVIS

We plan to expand Web JARVIS's features by incorporating more interactive components, such as enhanced user customization options and improved response accuracy. These enhancements aim to enrich the user experience further and broaden the application's appeal to a wider audience.